A two-level fusion approach to multimodal biometric verification

Ming Cheung Cheung; Man Wai Mak; Sun Yuan Kung

doi:10.1109/ICASSP.2005.1416346

A two-level fusion approach to multimodal biometric verification

Ming Cheung Cheung, Man Wai Mak, Sun Yuan Kung

The Hong Kong Polytechnic University

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

16 Citations (Scopus)

Abstract

This paper proposes a two-level fusion strategy for audio-visual biometric authentication. Specifically, fusion is performed at two levels: intramodal and intermodal. In intramodal fusion, the scores of multiple samples (e.g. utterances or video shots) obtained from the same modality are linearly combined, where the combination weights depend on the difference between the score values and a client-dependent reference score obtained during enrollment. This is followed by intermodal fusion in which the means of intramodal fused scores obtained from different modalities are either linearly combined or fused by a support vector machine (SVM). Experimental results based on the XM2VTSDB corpus show that intramodal and intermodal fusion are complementary to each other and that SVM-based intermodal fusion is superior to linear combination.

Original language	English
Title of host publication	2005 IEEE ICASSP '05 - Proc. - Design and Implementation of Signal Proces.Syst.,Indust. Technol. Track,Machine Learning for Signal Proces. Education, Spec. Sessions
Publisher	IEEE
Volume	V
ISBN (Print)	0780388747, 9780780388741
DOIs	https://doi.org/10.1109/ICASSP.2005.1416346
Publication status	Published - 1 Jan 2005
Event	2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05 - Philadelphia, PA, United States Duration: 18 Mar 2005 → 23 Mar 2005

Conference

Conference	2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05
Country/Territory	United States
City	Philadelphia, PA
Period	18/03/05 → 23/03/05

ASJC Scopus subject areas

Electrical and Electronic Engineering
Signal Processing
Acoustics and Ultrasonics

More information

10.1109/ICASSP.2005.1416346

Cite this

@inproceedings{15016bb937a54cc48268b21996b75a05,

title = "A two-level fusion approach to multimodal biometric verification",

abstract = "This paper proposes a two-level fusion strategy for audio-visual biometric authentication. Specifically, fusion is performed at two levels: intramodal and intermodal. In intramodal fusion, the scores of multiple samples (e.g. utterances or video shots) obtained from the same modality are linearly combined, where the combination weights depend on the difference between the score values and a client-dependent reference score obtained during enrollment. This is followed by intermodal fusion in which the means of intramodal fused scores obtained from different modalities are either linearly combined or fused by a support vector machine (SVM). Experimental results based on the XM2VTSDB corpus show that intramodal and intermodal fusion are complementary to each other and that SVM-based intermodal fusion is superior to linear combination.",

author = "Cheung, {Ming Cheung} and Mak, {Man Wai} and Kung, {Sun Yuan}",

year = "2005",

month = jan,

day = "1",

doi = "10.1109/ICASSP.2005.1416346",

language = "English",

isbn = "0780388747",

volume = "V",

booktitle = "2005 IEEE ICASSP '05 - Proc. - Design and Implementation of Signal Proces.Syst.,Indust. Technol. Track,Machine Learning for Signal Proces. Education, Spec. Sessions",

publisher = "IEEE",

address = "United States",

note = "2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05 ; Conference date: 18-03-2005 Through 23-03-2005",

}

Cheung, MC, Mak, MW & Kung, SY 2005, A two-level fusion approach to multimodal biometric verification. in 2005 IEEE ICASSP '05 - Proc. - Design and Implementation of Signal Proces.Syst.,Indust. Technol. Track,Machine Learning for Signal Proces. Education, Spec. Sessions. vol. V, 1416346, IEEE, 2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05, Philadelphia, PA, United States, 18/03/05. https://doi.org/10.1109/ICASSP.2005.1416346

A two-level fusion approach to multimodal biometric verification. / Cheung, Ming Cheung; Mak, Man Wai; Kung, Sun Yuan.
2005 IEEE ICASSP '05 - Proc. - Design and Implementation of Signal Proces.Syst.,Indust. Technol. Track,Machine Learning for Signal Proces. Education, Spec. Sessions. Vol. V IEEE, 2005. 1416346.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - A two-level fusion approach to multimodal biometric verification

AU - Cheung, Ming Cheung

AU - Mak, Man Wai

AU - Kung, Sun Yuan

PY - 2005/1/1

Y1 - 2005/1/1

N2 - This paper proposes a two-level fusion strategy for audio-visual biometric authentication. Specifically, fusion is performed at two levels: intramodal and intermodal. In intramodal fusion, the scores of multiple samples (e.g. utterances or video shots) obtained from the same modality are linearly combined, where the combination weights depend on the difference between the score values and a client-dependent reference score obtained during enrollment. This is followed by intermodal fusion in which the means of intramodal fused scores obtained from different modalities are either linearly combined or fused by a support vector machine (SVM). Experimental results based on the XM2VTSDB corpus show that intramodal and intermodal fusion are complementary to each other and that SVM-based intermodal fusion is superior to linear combination.

AB - This paper proposes a two-level fusion strategy for audio-visual biometric authentication. Specifically, fusion is performed at two levels: intramodal and intermodal. In intramodal fusion, the scores of multiple samples (e.g. utterances or video shots) obtained from the same modality are linearly combined, where the combination weights depend on the difference between the score values and a client-dependent reference score obtained during enrollment. This is followed by intermodal fusion in which the means of intramodal fused scores obtained from different modalities are either linearly combined or fused by a support vector machine (SVM). Experimental results based on the XM2VTSDB corpus show that intramodal and intermodal fusion are complementary to each other and that SVM-based intermodal fusion is superior to linear combination.

UR - http://www.scopus.com/inward/record.url?scp=33646780929&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2005.1416346

DO - 10.1109/ICASSP.2005.1416346

M3 - Conference article published in proceeding or book

SN - 0780388747

SN - 9780780388741

VL - V

BT - 2005 IEEE ICASSP '05 - Proc. - Design and Implementation of Signal Proces.Syst.,Indust. Technol. Track,Machine Learning for Signal Proces. Education, Spec. Sessions

PB - IEEE

T2 - 2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05

Y2 - 18 March 2005 through 23 March 2005

ER -

A two-level fusion approach to multimodal biometric verification

Abstract

Conference

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this